Instructions to use facebook/mask2former-swin-tiny-coco-instance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mask2former-swin-tiny-coco-instance with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="facebook/mask2former-swin-tiny-coco-instance")# Load model directly from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-tiny-coco-instance") model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-tiny-coco-instance") - Inference
- Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +27 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_max_size": 1333,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"ignore_index": 255,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48500001430511475,
|
| 9 |
+
0.4560000002384186,
|
| 10 |
+
0.4059999883174896
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Mask2FormerImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.2290000021457672,
|
| 15 |
+
0.2239999920129776,
|
| 16 |
+
0.22499999403953552
|
| 17 |
+
],
|
| 18 |
+
"num_labels": 80,
|
| 19 |
+
"reduce_labels": false,
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"height": 384,
|
| 24 |
+
"width": 384
|
| 25 |
+
},
|
| 26 |
+
"size_divisor": 32
|
| 27 |
+
}
|